From bf67cf7e4b42207e9e48b1de16d11c49a47279cc Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Tue, 24 Jan 2017 22:18:39 +0000
Subject: AMDGPU: Remove spurious out branches after a kill

The sequence like this:
  v_cmpx_le_f32_e32 vcc, 0, v0
  s_branch BB0_30
  s_cbranch_execnz BB0_30
  ; BB#29:
  exp null off, off, off, off done vm
  s_endpgm
  BB0_30:
  ; %endif110

is likely wrong. The s_branch instruction will unconditionally jump
to BB0_30 and the skip block (exp done + endpgm) inserted for
performing the kill instruction will never be executed. This results
in a GPU hang with Star Ruler 2.

The s_branch instruction is added during the "Control Flow Optimizer"
pass which seems to re-organize the basic blocks, and we assume
that SI_KILL_TERMINATOR is always the last instruction inside a
basic block. Thus, after inserting a skip block we just go to the
next BB without looking at the subsequent instructions after the
kill, and the s_branch op is never removed.

Instead, we should remove the unconditional out branches and let
skip the two instructions if the exec mask is non-zero.

This patch fixes the GPU hang and doesn't introduce any regressions
with "make check".

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=99019

Patch by Samuel Pitoiset <samuel.pitoiset@gmail.com>

llvm-svn: 292985
---
 llvm/lib/Target/AMDGPU/SIInsertSkips.cpp | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'llvm/lib')

diff --git a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
index c6b420fce8a..9d6feaa94fb 100644
--- a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
@@ -263,6 +263,7 @@ bool SIInsertSkips::runOnMachineFunction(MachineFunction &MF) {
        BI != BE; BI = NextBB) {
     NextBB = std::next(BI);
     MachineBasicBlock &MBB = *BI;
+    bool HaveSkipBlock = false;
 
     if (!ExecBranchStack.empty() && ExecBranchStack.back() == &MBB) {
       // Reached convergence point for last divergent branch.
@@ -290,8 +291,14 @@ bool SIInsertSkips::runOnMachineFunction(MachineFunction &MF) {
       case AMDGPU::S_BRANCH:
         // Optimize out branches to the next block.
         // FIXME: Shouldn't this be handled by BranchFolding?
-        if (MBB.isLayoutSuccessor(MI.getOperand(0).getMBB()))
+        if (MBB.isLayoutSuccessor(MI.getOperand(0).getMBB())) {
           MI.eraseFromParent();
+        } else if (HaveSkipBlock) {
+          // Remove the given unconditional branch when a skip block has been
+          // inserted after the current one and let skip the two instructions
+          // performing the kill if the exec mask is non-zero.
+          MI.eraseFromParent();
+        }
         break;
 
       case AMDGPU::SI_KILL_TERMINATOR:
@@ -300,9 +307,9 @@ bool SIInsertSkips::runOnMachineFunction(MachineFunction &MF) {
 
         if (ExecBranchStack.empty()) {
           if (skipIfDead(MI, *NextBB)) {
+            HaveSkipBlock = true;
             NextBB = std::next(BI);
             BE = MF.end();
-            Next = MBB.end();
           }
         } else {
           HaveKill = true;
-- 
cgit v1.2.3